• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.706-709
• /
• 2006

Cancer is one of the major causes of death; however, the survival rate can be increased if discovered at an early stage for timely treatment. According to the statistics of the World Health Organization of 2002, breast cancer was the most prevalent cancer for all cancers occurring in women worldwide, and it account for 16.8% of entire cancers inflicting Korean women today. In order to classify the type of breast cancer whether it is benign or malignant, this study was conducted with the use of the discriminant analysis and the decision tree of data mining with the breast cancer data disclosed on the web. The discriminant analysis is a statistical method to seek certain discriminant criteria and discriminant function to separate the population groups on the basis of observation values obtained from two or more population groups, and use the values obtained to allow the existing observation value to the population group thereto. The decision tree analyzes the record of data collected in the part to show it with the pattern existing in between them, namely, the combination of attribute for the characteristics of each class and make the classification model tree. Through this type of analysis, it may obtain the systematic information on the factors that cause the breast cancer in advance and prevent the risk of recurrence after the surgery.

• Proceedings of the KSRS Conference
• /
• 2008.03a
• /
• pp.195-200
• /
• 2008

The accuracy of classifying pixels in HIRIS images is usually degraded by noisy bands since noisy bands may deform the typical shape of spectral reflectance. Proposed in this paper is a statistical method for noisy band removal which mainly makes use of the correlation coefficients between bands. Considering each band as a random variable, the correlation coefficient measures the strength and direction of a linear relationship between two random variables. While the correlation between two signal bands is high, existence of a noisy band will produce a low correlation due to ill-correlativeness and undirectedness. The application of the correlation coefficient as a measure for detecting noisy bands is under a two-pass screening scheme. This method is independent of the prior knowledge of the sensor or the cause resulted in the noise. The classification in this experiment uses the unsupervised k-nearest neighbor algorithm in accordance with the well-accepted Euclidean distance measure and the spectral angle mapper measure. This paper also proposes a hierarchical combination of these measures for spectral matching. Finally, a separability assessment based on the between-class and within-class scatter matrices is followed to evaluate the performance.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2002.03a
• /
• pp.45-52
• /
• 2002

Artificial neural networks (ANN) have been successfully used for classifying remotely sensed imagery. However, ANN still is not the preferable choice for classification over the conventional classification methodology such as the maximum likelihood classifier commonly used in the industry production environment. This can be attributed to the ANN characteristic built-in stochastic process that creates difficulties in dealing with unequally represented training classes, and its training performance speed. In this paper we examined some practical aspects of training classes when using a back propagation neural network model for remotely sensed imagery. During the classification process of remotely sensed imagery, representative training patterns for each class are collected by polygons or by using a region-growing methodology over the imagery. The number of collected training patterns for each class may vary from several pixels to thousands. This unequally populated training data may cause the significant problems some neural network empirical models such as back-propagation have experienced. We investigate the effects of training over- or under- represented training patterns in classes and propose the pattern repopulation algorithm, and an adaptive alpha adjustment (AAA) algorithm to handle unequally represented classes. We also show the performance improvement when input patterns are presented in random fashion during the back-propagation training.

• Geomechanics and Engineering
• /
• v.20 no.2
• /
• pp.113-120
• /
• 2020

Rock damage is the main cause of accidents in underground engineering. It is difficult to predict rock damage accurately by using only one parameter. In this study, a rock failure prediction model was established by using stress, energy, and damage. The prediction level was divided into three levels according to the ratio of the damage threshold stress to the peak stress. A classification predicting model was established, including the stress, energy, damage and AE impact rate using Bayesian method. Results show that the model is good practicability and effectiveness in predicting the degree of rock failure. On the basis of this, a multi-parameter classification predicting deterioration model of rock failure was established. The results provide a new idea for classifying and predicting rockburst.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2003.06b
• /
• pp.119-137
• /
• 2003

Electrical resistivity is one of physical property of the earth and measured by electrical resistivity survey, electrical resistivity logging and laboratory test. Recently, electrical resistivity Is widely used In determination of rock quality in road and railway tunnel design. To get more reliable rock quality data from electrical resistivity, it needs a lot of test and study on correlation of resistivity and rock quality. Firstly, we did rock property test In laboratory, such as uniaxial compressive strength(UCS), P wave velocity, Young's modulus and electrical resistivity. We correlate each test results and we found out that electrical resistivity has exponentially related to UCS and P wave velocity and linearly related to Young's modulus. And we accomplished electrical resistivity survey in field site and carried out electrical resistivity togging at In-situ area. Also we performed rock classification, such as RQD, RMR and Q-system and we correlate electrical resistivity to rock classification results. We found out that electrical resistivity logging data are highly correlate to RQD, Q and RMR. Also we found out that electrical resistivity survey data are lower than electrical resistivity logging data when there are faults or fractures. And it cause electrical resistivity survey data to lowly correlate to RQD, Q and RMR.

• KIEAE Journal
• /
• v.9 no.1
• /
• pp.31-38
• /
• 2009

The purpose of this study is to present direction in outdoors space planning and design after direction through user characteristic analysis through spectacle component establishment of culture art center outdoors space through on-the-site analysis and literature investigation to culture art center of Seoul city and capital region 17 places in this research. The data was collected from classification and bisection kind, subdivision kind, and great classification composed to 17 items. User satisfaction side and Variable that is looked below satisfaction than average appeared to bench, pergola, sculpture facilities, pavement facilities, border facilities. And these facilities were analyzed dissatisfaction. When see satisfaction model, when make up culture art center or similar facilities in local government hereafter because parking facilities and rest area cause big effect in satisfaction, is judged that is item to consider most preferentially. In most case, parking lot security from outdoors space, resting place security, security of field performance facilities etc. taking a serious view because tendency that users see performance or use most vehicles except neighborhood walking area for a rest, a walk etc.. is trend. But, is judged that physical side so that can feel satisfaction as space security of quantitative side is important but users utilize substantially and side that is the program are more important in hereafter.

• Proceedings of the Korean Institute of Landscape Architecture Conference
• /
• 2007.10b
• /
• pp.151-156
• /
• 2007

The Eight Scenery, as a traditional landscape to today, gradually caught the concern of landscape scholars, as well became the mutual cultural wealth of South Korea, China and Japan even of the whole Asia. The Yanjing Eight Scenery firstly originated from the Jin dynasty is an important representation of Eight Scenery culture in Scenic Spots and Historical Sites of China. The transition process of Yanjing Eight Scenery is examined in this thesis, and the cause of such change is also analyzed. Moreover, the landscape content of Yanjing Eight Scenery is classified in detail, and the succession of the landscape architecture of the Yanjing Eight Scenery style under the traditional culture is analyzed from the aspects of rebuilding pavilion, landscape arrangement, building, and new landscape architecture rebuilt followed the religious, the plant landscape and the traditional culture based on the classification. Beijing regional culture has influenced Yanjing Eight Scenery by its classification, the landscape evaluation, and the analysis of the landscape feature, in addition, this paper searches for the model to research the Eight Scenery culture in each country of Asia.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.11a
• /
• pp.796-801
• /
• 2000

The monitoring and diagnostics of the rotating machinery have been received considerable attention for many years. The objectives are to classify the machinery condition and to find out the cause of abnormal condition. This paper describes a signal classification method for diagnosing the rotating machinery using the artificial neural network and the wavelet transform. In order to extract salient features, the wavelet transform are used from primary noise signals. Since the wavelet transform decomposes raw time-waveform signals into two respective parts in the time space and frequency domain, more and better features can be obtained easier than time-waveform analysis. In the training phase for classification, self-organizing feature map(SOFM) and learning vector quantization(LVQ) are applied, and the accuracies of them are compared with each other. This paper is focused on the development of an advanced signal classifier to automatise the vibration signal pattern recognition. This method is verified by small reciprocating compressors, for refrigerator and normal and abnormal conditions are classified with high flexibility and reliability.

• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.803-812
• /
• 2019

Triplex composite is an epoxy-bonded joint structure, which constitutes the secondary barrier in a liquefied natural gas (LNG) carrier. Defects in the triplex composite weaken its shear strength and may cause leakage of the LNG, thus compromising the structural integrity of the LNG carrier. This paper proposes an autonomous triplex composite inspection (ATCI) system for visualizing and classifying hidden defects in the triplex composite installed inside an LNG carrier. First, heat energy is generated on the surface of the triplex composite using halogen lamps, and the corresponding heat response is measured by an infrared (IR) camera. Next, the region of interest (ROI) is traced and noise components are removed to minimize false indications of defects. After a defect is identified, it is classified as internal void or uncured adhesive and its size and shape are quantified and visualized, respectively. The proposed ATCI system allows the fully automated and contactless detection, classification, and quantification of hidden defects inside the triplex composite. The effectiveness of the proposed ATCI system is validated using the data obtained from actual triplex composite installed in an LNG carrier membrane system.

• Smart Media Journal
• /
• v.8 no.3
• /
• pp.31-40
• /
• 2019

To understand how a Convolutional Neural Network (CNN) model captures the features of a pattern to determine which class it belongs to, in this paper, we use Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize and analyze how well a CNN model behave on the CNU weeds dataset. We apply this technique to Resnet model and figure out which features this model captures to determine a specific class, what makes the model get a correct/wrong classification, and how those wrong label images can cause a negative effect to a CNN model during the training process. In the experiment, Grad-CAM highlights the important regions of weeds, depending on the patterns learned by Resnet, such as the lobe and limb on 미국가막사리, or the entire leaf surface on 단풍잎돼지풀. Besides, Grad-CAM points out a CNN model can localize the object even though it is trained only for the classification problem.